The Rules Determination of Numerical Association Rule Mining Optimization by Using Combination of PSO and Cauchy Distribution
One of the optimization methods to solve the numerical association rule mining problem is particle swarm optimization (PSO). This method is popularly used in various fields such as in the job scheduling problem, evaluating stock market, inferring gen regulatory networks and numerical association rule mining optimization. The weakness of the PSO is often premature for searching the optimal solution because it traps in local optima when the best particle is being searched in every iteration. Combining the PSO with Cauchy distribution for numerical association rule mining problem (PARCD) is a solution because it is robust for finding the optimal solution in a large neighborhood. The important point in this proposed method is particle representation which to know the association between one attribute to another. Therefore, this study has the aim to determinate rules of numerical association rule mining and also to calculate the multi-objective function using combination of PSO and Cauchy distribution. The results show that all of them explain every attribute to formulate the rule well. In addition, the multi-objective function value of PARCD method generally produces results which better than the previous method, MOPAR.
KeywordsPSO Cauchy distribution Numerical association rule mining Particle representation Multi-objective functions PARCD MOPAR
This research supported by various parties. We would like to thank for scholarship program from Kanazawa University, Japan and Ministry of Research and Technology and Directorate of Higher Education (KEMENRISTEKDIKTI) and also STMIK AMIKOM Purwokerto, Indonesia. In addition, we thank for anonymous reviewers who gave input and correction for improving this research.
- 5.Arotaritei D, Negoita MG (2003) An optimization of data mining algorithms used in fuzzy association rules. In: International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. Springer, Heidelberg, pp 980–985Google Scholar
- 7.Gen M, Lin L, Howada (2015) Hybrid evolutionary algorithms and data mining: case studies of clustering. Proc Soc Plant Eng 2015:184–196Google Scholar
- 11.Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, vol 4, pp 1942–1948Google Scholar
- 12.Li C, Liu Y et al (2007) A fast particle swarm optimization algorithm with cauchy mutation and natural selection strategy. In: International Symposium on Intelligence Computation and Applications. Springer, Heidelberg, pp 334–343Google Scholar
- 14.Narita M, Haraguchi M, Okubo Y (2002) Data abstractions for numerical attributes in data mining. Lecture Notes in Computer Science, vol 2412, pp 35–42Google Scholar
- 18.Tahyudin I, Nambo H (2017) The combination of evolutionary algorithm method for numerical association rule mining optimization. In: Proceedings of the Tenth International Conference on Management Science and Engineering Management. Springer, Heidelberg, pp 13–23Google Scholar